Harnessing Chemical Space Neural Networks to Systematically Annotate GPCR ligands

Harnessing Chemical Space Neural Networks to Systematically Annotate GPCR ligands | Research Square window.SnipcartSettings = { analytics: { enabled: false } }; (function() { var accessVector = localStorage.getItem('access_vector') || ''; window.dataLayer = window.dataLayer || []; if (accessVector) { window.dataLayer.push({ user: { profile: { profileInfo: { snid: accessVector } } } }); } })(); (function(w,d,s,l,i){w[l]=w[l]||[];w[l].push({'gtm.start':new Date().getTime(),event:'gtm.js'});var f=d.getElementsByTagName(s)[0],j=d.createElement(s),dl=l!='dataLayer'?'&l='+l:'';j.async=true;j.src='https://www.googletagmanager.com/gtm.js?id='+i+dl;f.parentNode.insertBefore(j,f);})(window,document,'script','dataLayer','GTM-K279D39R'); Browse Preprints In Review Journals COVID-19 Preprints AJE Video Bytes Research Tools Research Promotion AJE Professional Editing AJE Rubriq About Preprint Platform In Review Editorial Policies Our Team Advisory Board Help Center Sign In Submit a Preprint Cite Share Download PDF Article Harnessing Chemical Space Neural Networks to Systematically Annotate GPCR ligands Emil Jensen, Frederik Hansson, Niklas Gesmar Madsen, Lea Hansen, and 5 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-4287546/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 03 May, 2025 Read the published version in Nature Communications → Version 1 posted You are reading this latest preprint version Abstract Drug-target interaction (DTI) databases comprise millions of manually curated data points, yet there are missed opportunities for repurposing established interaction networks to infer DTIs. To address this gap, we first collected DTIs on 128 unique G protein-coupled receptors across 187K molecules to establish an all-vs-all chemical space network. We next developed a chemical space neural network (CSNN), which operates on the graph structure of chemical space rather than on the graphs of compounds, to infer drug bioactivity classes with up to 98% accuracy. We combined this virtual library screen with a cost-efficient experimental platform to validate our predictions and discovered 14 novel DTIs in the process. Altogether, our platform integrates virtual library screening and experimental validation for fast and efficient coverage of missing DTIs. Biological sciences/Computational biology and bioinformatics/Machine learning Biological sciences/Chemical biology/Cheminformatics Biological sciences/Drug discovery/Drug screening/High-throughput screening Biological sciences/Drug discovery/Drug screening/Virtual screening Biological sciences/Drug discovery/Target identification Full Text Additional Declarations Yes there is potential Competing Interest. J.D.K., L.G.H., and M.K.J. are inventors on pending patent applications (patent applicant: Technical University of Denmark; application number: PCT/EP2023/063481). L.G.H., J.D.K. and M.K.J. have financial interests in Biomia. J.D.K. also has financial interests in Amyris, Lygos, Demetrix, Napigen, Apertor Pharmaceuticals, Maple Bio, Ansa Biotechnologies, Berkeley Yeast and Zero Acre Farms. All other authors have no competing interests. Supplementary Files Hanssonetalsuppl.docx Harnessing Chemical Space Neural Networks to Systematically Annotate GPCR ligands SupplementaryFileS1Completedataset.csv Supplementary File S1 SupplementaryfileS2assaypricing.xlsx Supplementary File S2 SupplementaryfileS3DRCsupportinginformation.xlsx Supplementary File S3 SupplementaryFileS4ChEMBLcleanedandIUPHAR.csv Supplementary File S4 Cite Share Download PDF Status: Published Journal Publication published 03 May, 2025 Read the published version in Nature Communications → Version 1 posted You are reading this latest preprint version Research Square lets you share your work early, gain feedback from the community, and start making changes to your manuscript prior to peer review in a journal. As a division of Research Square Company, we’re committed to making research communication faster, fairer, and more useful. We do this by developing innovative software and high quality services for the global research community. Our growing team is made up of researchers and industry professionals working together to solve the most critical problems facing scientific publishing. Also discoverable on Platform About Our Team In Review Editorial Policies Advisory Board Help Center Resources Author Services Accessibility API Access RSS feed Manage Cookie Preferences © Research Square 2026 | ISSN 2693-5015 (online) Privacy Policy Terms of Service Do Not Sell My Personal Information {"props":{"pageProps":{"initialData":{"identity":"rs-4287546","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":308683614,"identity":"85ea8012-b364-46f5-bcd0-db17f70e49ec","order_by":0,"name":"Emil Jensen","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAABB0lEQVRIiWNgGAWjYHACAwYJBpsENiiPByzCwMBsQEBLGlRLAliLYQNBLQwMhxMYoFoYCGrhFzu88YNFxfk8Pvb2Z5I/f9jJmDMwb3/Mw2BtjEuL5Oy0YgmJM7eL2XjOmEnzJCTzWDawFTbzMKSb4XTV7RwDCcm224ltEjls0gwJzDwGB3gMgVoO2+DSYn87x/iH5L9zQC3pzyR/JNQT1mIgnWMmIdlwAKglwUyCJ+EwXAtOh0ncTiuzkDiWDPKLsTVP2nEeg8NshTPnGKTj9D7/7OTNtyVq7PLk29sf3vxhU21vcLx5w4c3FdagkMYJmCVQuWAH41EPBIwf8MuPglEwCkbBSAcAceVNzbR37V8AAAAASUVORK5CYII=","orcid":"https://orcid.org/0000-0002-8280-0946","institution":"Technical University of Denmark","correspondingAuthor":true,"prefix":"","firstName":"Emil","middleName":"","lastName":"Jensen","suffix":""},{"id":308683615,"identity":"c5bde6a1-1cad-4dd0-85d7-d460f4d5c745","order_by":1,"name":"Frederik Hansson","email":"","orcid":"","institution":"Technical University of Denmark","correspondingAuthor":false,"prefix":"","firstName":"Frederik","middleName":"","lastName":"Hansson","suffix":""},{"id":308683616,"identity":"342e6408-55b2-41d4-9713-c1e01eab9e12","order_by":2,"name":"Niklas Gesmar Madsen","email":"","orcid":"https://orcid.org/0009-0001-4599-4040","institution":"Technical University of Denmark","correspondingAuthor":false,"prefix":"","firstName":"Niklas","middleName":"Gesmar","lastName":"Madsen","suffix":""},{"id":308683617,"identity":"45de186a-2474-4aa3-b5b8-80b499a29908","order_by":3,"name":"Lea Hansen","email":"","orcid":"","institution":"Biomia ApS","correspondingAuthor":false,"prefix":"","firstName":"Lea","middleName":"","lastName":"Hansen","suffix":""},{"id":308683618,"identity":"eddcf486-2f4c-4702-9a46-bc892f839bea","order_by":4,"name":"Tadas Jakočiūnas","email":"","orcid":"","institution":"Technical University of Denmark","correspondingAuthor":false,"prefix":"","firstName":"Tadas","middleName":"","lastName":"Jakočiūnas","suffix":""},{"id":308683619,"identity":"a40eb0be-1fe7-4b15-8173-492a007b34cf","order_by":5,"name":"Bettina Lengger","email":"","orcid":"","institution":"Technical University of Denmark","correspondingAuthor":false,"prefix":"","firstName":"Bettina","middleName":"","lastName":"Lengger","suffix":""},{"id":308683620,"identity":"90f2b6e4-fa1c-4a5c-a7ab-14fc2c48734c","order_by":6,"name":"Jay Keasling","email":"","orcid":"https://orcid.org/0000-0003-4170-6088","institution":"Joint BioEnergy Institute","correspondingAuthor":false,"prefix":"","firstName":"Jay","middleName":"","lastName":"Keasling","suffix":""},{"id":308683621,"identity":"93baeaef-12f0-47a3-8451-b9cc2c01a11e","order_by":7,"name":"Michael Jensen","email":"","orcid":"","institution":"Technical University of Denmark","correspondingAuthor":false,"prefix":"","firstName":"Michael","middleName":"","lastName":"Jensen","suffix":""},{"id":308683622,"identity":"120a5185-8ffc-4d11-9af4-be996566cbd0","order_by":8,"name":"Carlos Acevedo-Rocha","email":"","orcid":"","institution":"Technical University of Denmark","correspondingAuthor":false,"prefix":"","firstName":"Carlos","middleName":"","lastName":"Acevedo-Rocha","suffix":""}],"badges":[],"createdAt":"2024-04-18 11:50:09","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-4287546/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-4287546/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1038/s41467-025-59418-6","type":"published","date":"2025-05-03T04:00:00+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":81866935,"identity":"3a1fc5fa-a525-4424-88f7-229870e25071","added_by":"auto","created_at":"2025-05-03 07:06:31","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":941211,"visible":true,"origin":"","legend":"","description":"","filename":"Hanssonetalmanuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-4287546/v1_covered_a692d799-e3e5-4e7d-8cd2-a5fd99599f90.pdf"},{"id":58250906,"identity":"a7bc7a57-eb25-43d9-bb1d-ae697a4d6c3a","added_by":"auto","created_at":"2024-06-13 03:17:42","extension":"docx","order_by":1,"title":"","display":"","copyAsset":false,"role":"supplement","size":20900608,"visible":true,"origin":"","legend":"Harnessing Chemical Space Neural Networks to Systematically Annotate GPCR ligands","description":"","filename":"Hanssonetalsuppl.docx","url":"https://assets-eu.researchsquare.com/files/rs-4287546/v1/a9413715619d7b912098a400.docx"},{"id":58250904,"identity":"1c867a2e-ffa3-4e5d-a218-d2eef777dae6","added_by":"auto","created_at":"2024-06-13 03:17:42","extension":"csv","order_by":2,"title":"","display":"","copyAsset":false,"role":"supplement","size":1320752,"visible":true,"origin":"","legend":"\u003cp\u003eSupplementary File S1\u003c/p\u003e","description":"","filename":"SupplementaryFileS1Completedataset.csv","url":"https://assets-eu.researchsquare.com/files/rs-4287546/v1/cf527ddaf454b6d5ffd79fe3.csv"},{"id":58250907,"identity":"38a49cd8-9af2-48fc-9367-f52cfc1245e3","added_by":"auto","created_at":"2024-06-13 03:17:42","extension":"xlsx","order_by":3,"title":"","display":"","copyAsset":false,"role":"supplement","size":19791,"visible":true,"origin":"","legend":"\u003cp\u003eSupplementary File S2\u003c/p\u003e","description":"","filename":"SupplementaryfileS2assaypricing.xlsx","url":"https://assets-eu.researchsquare.com/files/rs-4287546/v1/4aa62873a6e78f4b80b9b394.xlsx"},{"id":58250905,"identity":"ff740de4-c58f-45f5-8a95-e984c90293d5","added_by":"auto","created_at":"2024-06-13 03:17:42","extension":"xlsx","order_by":4,"title":"","display":"","copyAsset":false,"role":"supplement","size":19226,"visible":true,"origin":"","legend":"\u003cp\u003eSupplementary File S3\u003c/p\u003e","description":"","filename":"SupplementaryfileS3DRCsupportinginformation.xlsx","url":"https://assets-eu.researchsquare.com/files/rs-4287546/v1/3f614fcd406b24df871e66f1.xlsx"},{"id":58250908,"identity":"b5d1bbbf-8ee0-47da-bbf5-27607296c2eb","added_by":"auto","created_at":"2024-06-13 03:17:43","extension":"csv","order_by":5,"title":"","display":"","copyAsset":false,"role":"supplement","size":50797438,"visible":true,"origin":"","legend":"\u003cp\u003eSupplementary File S4\u003c/p\u003e","description":"","filename":"SupplementaryFileS4ChEMBLcleanedandIUPHAR.csv","url":"https://assets-eu.researchsquare.com/files/rs-4287546/v1/bde738f4036743f8e864fbb9.csv"}],"financialInterests":"\u003cb\u003eYes\u003c/b\u003e there is potential Competing Interest.\nJ.D.K., L.G.H., and M.K.J. are inventors on pending\r\npatent applications (patent applicant: Technical University of Denmark; application number: PCT/EP2023/063481). L.G.H.,\r\nJ.D.K. and M.K.J. have financial interests in Biomia. J.D.K. also has\r\nfinancial interests in Amyris, Lygos, Demetrix, Napigen, Apertor Pharmaceuticals, Maple Bio, Ansa Biotechnologies, Berkeley Yeast and Zero Acre Farms. All other authors have no competing interests.","formattedTitle":"Harnessing Chemical Space Neural Networks to Systematically Annotate GPCR ligands","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"hideJournal":false,"highlight":"","institution":"","isAcceptedByJournal":true,"isAuthorSuppliedPdf":true,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":true,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"nature-portfolio","isNatureJournal":true,"hasQc":false,"allowDirectSubmit":false,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"","title":"Nature Portfolio","twitterHandle":"","acdcEnabled":false,"dfaEnabled":false,"editorialSystem":"ejp","reportingPortfolio":"","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"","lastPublishedDoi":"10.21203/rs.3.rs-4287546/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-4287546/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eDrug-target interaction (DTI) databases comprise millions of manually curated data points, yet there are missed opportunities for repurposing established interaction networks to infer DTIs. To address this gap, we first collected DTIs on 128 unique G protein-coupled receptors across 187K molecules to establish an all-vs-all chemical space network. We next developed a chemical space neural network (CSNN), which operates on the graph structure of chemical space rather than on the graphs of compounds, to infer drug bioactivity classes with up to 98% accuracy. We combined this virtual library screen with a cost-efficient experimental platform to validate our predictions and discovered 14 novel DTIs in the process. Altogether, our platform integrates virtual library screening and experimental validation for fast and efficient coverage of missing DTIs.\u003c/p\u003e","manuscriptTitle":"Harnessing Chemical Space Neural Networks to Systematically Annotate GPCR ligands","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-06-13 03:17:37","doi":"10.21203/rs.3.rs-4287546/v1","editorialEvents":[],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"nature-communications","isNatureJournal":true,"hasQc":false,"allowDirectSubmit":false,"externalIdentity":"NCOMMS","sideBox":"Learn more about [Nature Communications](http://www.nature.com/ncomms/)","snPcode":"","submissionUrl":"https://mts-ncomms.nature.com/","title":"Nature Communications","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"ejp","reportingPortfolio":"Nature Communications","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"1a2d8578-9d60-4e96-b0d0-6f7c8de23ac7","owner":[],"postedDate":"June 13th, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[{"id":32611082,"name":"Biological sciences/Computational biology and bioinformatics/Machine learning"},{"id":32611083,"name":"Biological sciences/Chemical biology/Cheminformatics"},{"id":32611084,"name":"Biological sciences/Drug discovery/Drug screening/High-throughput screening"},{"id":32611085,"name":"Biological sciences/Drug discovery/Drug screening/Virtual screening"},{"id":32611086,"name":"Biological sciences/Drug discovery/Target identification"}],"tags":[],"updatedAt":"2025-05-03T07:06:25+00:00","versionOfRecord":{"articleIdentity":"rs-4287546","link":"https://doi.org/10.1038/s41467-025-59418-6","journal":{"identity":"nature-communications","isVorOnly":false,"title":"Nature Communications"},"publishedOn":"2025-05-03 04:00:00","publishedOnDateReadable":"May 3rd, 2025"},"versionCreatedAt":"2024-06-13 03:17:37","video":"","vorDoi":"10.1038/s41467-025-59418-6","vorDoiUrl":"https://doi.org/10.1038/s41467-025-59418-6","workflowStages":[]},"version":"v1","identity":"rs-4287546","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-4287546","identity":"rs-4287546","version":["v1"]},"buildId":"qtupq5eGEP_6zYnWcrvyt","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}